Scholar
Chris Donahue
Google Scholar ID: MgzHAPQAAAAJ
Assistant Professor, CMU CSD; Research Scientist, Google DeepMind (part time)
Citations & Impact
Citations
10,591
H-index
23
i10-index
25
Publications
20
Co-authors
45
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Multiple papers accepted at conferences such as ISMIR, WASPAA, ICML, etc.; Led the development of Magenta RealTime; Collaborated with PhD student Wayne Chi on research that received the Best Paper Award at the NAACL Student Research Workshop 2025; Paper on AMUSE recognized with a Best Paper Award at CHI 2025; Other research works have been acknowledged by the industry.
Research Experience
- Research Scientist (part-time) at Google DeepMind on the Magenta team, leading the development of new open weights real-time music generation model: Magenta RealTime; Worked on Piano Genie, which was used in a live performance by The Flaming Lips; Also worked on Dance Dance Convolution, powering Beat Sage, a live service used by thousands of users daily to create multimodal music game content.
Education
- Ph.D. from UCSD, co-advised by Miller Puckette and Julian McAuley; Postdoc at Stanford CS advised by Percy Liang.
Background
- Dannenberg Assistant Professor in the Computer Science Department at Carnegie Mellon University, and also a Research Scientist at Google DeepMind on the Magenta team (part-time). His research goal is to develop and responsibly deploy generative AI for music and creativity, thereby unlocking and augmenting human creative potential. This involves improving machine learning methods for controllable generative modeling for music, audio, and other sequential data, and deploying real-world interactive systems that allow a broader audience to harness generative music AI through intuitive controls.
Miscellany
- Interested in applying research ideas to real-world applications and often builds systems for real users to be evaluated in-the-wild.
